arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.07386cs.CV
收藏

基于组合ConvNets的流式突触检测

Toward Streaming Synapse Detection with Compositional ConvNets

Massachusetts Institute of Technology(麻省理工学院)

Shibani Santurkar, David Budden, Alexander Matveev, Heather Berlin, Hayk Saribekyan, Yaron Meirovitch, Nir Shavit

摘要:

连接组学是神经科学中的一个新兴领域,旨在从电子显微镜(EM)图像重建神经元的三维形态。最近的研究已经成功地证明了使用卷积神经网络(ConvNets)来分割细胞膜以个体化神经元。然而,在高通量识别细胞间突触连接所需的导出连接图方面,已经取得了比较小的成功。在这项研究中,我们采取的组成方法分割突触,明确建模为一个细胞间的间隙共同位于沿细胞膜的不对称囊泡密度。我们不需要一个深度网络来学习这种组合的所有自然组合,而是训练更轻的网络来模拟来自100个电子显微镜样品的膜、裂缝和囊泡的更简单的边缘分布。然后将这些特征图与来自先前生物学知识的简单的基于规则的分类相结合。我们的突触检测方法比以前的最新技术更准确(召回率高7%,F1分数高5%),并且与以前最快的实现相比,速度提高了20倍。我们证明重建第一个完整的,定向连接体从最大的可用各向异性显微镜数据集(245 GB)的小鼠体感皮层(S1)在短短9.7小时在一个单一的共享内存CPU系统。我们相信,这项工作标志着朝着显微镜速度流式连接组学管道的目标迈出了重要一步。

英文摘要:

Connectomics is an emerging field in neuroscience that aims to reconstruct the 3-dimensional morphology of neurons from electron microscopy (EM) images. Recent studies have successfully demonstrated the use of convolutional neural networks (ConvNets) for segmenting cell membranes to individuate neurons. However, there has been comparatively little success in high-throughput identification of the intercellular synaptic connections required for deriving connectivity graphs. In this study, we take a compositional approach to segmenting synapses, modeling them explicitly as an intercellular cleft co-located with an asymmetric vesicle density along a cell membrane. Instead of requiring a deep network to learn all natural combinations of this compositionality, we train lighter networks to model the simpler marginal distributions of membranes, clefts and vesicles from just 100 electron microscopy samples. These feature maps are then combined with simple rules-based heuristics derived from prior biological knowledge. Our approach to synapse detection is both more accurate than previous state-of-the-art (7% higher recall and 5% higher F1-score) and yields a 20-fold speed-up compared to the previous fastest implementations. We demonstrate by reconstructing the first complete, directed connectome from the largest available anisotropic microscopy dataset (245 GB) of mouse somatosensory cortex (S1) in just 9.7 hours on a single shared-memory CPU system. We believe that this work marks an important step toward the goal of a microscope-pace streaming connectomics pipeline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑